Chronos: A general purpose classical AMG solver for High Performance Computing

@article{Isotton2021ChronosAG,
  title={Chronos: A general purpose classical AMG solver for High Performance Computing},
  author={Giovanni Isotton and Matteo Frigo and Nicol{\`o} Spiezia and Carlo Janna},
  journal={SIAM J. Sci. Comput.},
  year={2021},
  volume={43},
  pages={C335-C357}
}
The numerical simulation of the physical systems has become in recent years a fundamental tool to perform analyses and predictions in several application fields, spanning from industry to the academy. As far as large scale simulations are concerned, one of the most computationally expensive task is the solution of linear systems arising from the discretization of the partial differential equations governing the physical processes. This work presents Chronos, a collection of linear algebra… 

Parallel Energy-Minimization Prolongation for Algebraic Multigrid

A constrained minimization procedure aimed at reducing prolongation energy while preserving the near kernel components in the span of interpolation is proposed and shown that the resulting solver exhibits excellent convergence rates and scalability and outperforms at least some more traditional AMG approaches.

A Reverse Augmented Constraint preconditioner for Lagrange multiplier methods in contact mechanics

On the construction of AMG prolongation through energy minimization

This work presents an updated prolongation according to an energy minimization criterion and shows how this minimization can be seen as a constrained minimization problem.

Parallel Matrix-free polynomial preconditioners with application to flow simulations in discrete fracture networks

A robust matrix-free, communication avoiding parallel, high-degree polynomial preconditioner for the Conjugate Gradient method for large and sparse symmetric positive definite linear systems and uses this framework to solve a 3 × 3 block system arising in the simulation of large-size discrete fractured networks.

Explicit caching HYB: a new high-performance SpMV framework on GPGPU

This study is trying to minimize the data movements cost for GPU based SpMV using a new framework named” explicit caching Hybrid (EHYB”, which can overperform the state-of-the-arts implementation with significant speedup, and leads to higher FLOPs than the theoryperformance up-boundary of the existing GPU-based SpMv implementations.

FRAME2020+2 Practical Info and Conference Program

This talk reviews the nodal Vertex Approximate Gradient (VAG) discretization of two-phase Darcy flows in fractured porous media for which the fracture network is represented as a manifold of co-dimension one with respect to the surrounding matrix domain.

References

SHOWING 1-10 OF 54 REFERENCES

A GPU-accelerated adaptive FSAI preconditioner for massively parallel simulations

This work shows how adaptive Factored Sparse Approximate Inverse (aFSAI), characterized by a very high degree of parallelism, can be successfully implemented on a distributed memory computer equipped with GPU accelerators.

Scalability Challenges of an Industrial Implicit Finite Element Code

This paper investigates the scalability challenges of the implicit structural mode of LS- DYNA, and focuses on linear constraint analysis, sparse matrix reordering, symbolic factorization, and numerical factorization.

FP-AMG: FPGA-Based Acceleration Framework for Algebraic Multigrid Solvers

This work proposes an efficient FPGA-based reconfigurable framework, called FP-AMG, for high-performance AMG calculation, and proposes a novel and scalable architecture that can be reused for all kernels in AMG.

BoomerAMG: a parallel algebraic multigrid solver and preconditioner

A robust adaptive algebraic multigrid linear solver for structural mechanics

Non-Galerkin Coarse Grids for Algebraic Multigrid

Algebraic multigrid is a popular and effective solver for systems of linear equations that arise from discretized partial differential equations, but challenges remain, especially when moving to exascale.

Algebraic Multigrid

In computer simulation of particular systems (e.g. in physics, biology, economics), partial differential equations (PDE) are solved numerically, mainly by applying Finite Element (FE) or Finite

Adaptive Smoothed Aggregation (AlphaSA) Multigrid

An extension of the SA method in which good convergence properties are achieved in situations where explicit knowledge of the near-kernel components is unavailable is introduced in an adaptive process that uses the method itself to determine near- kernel components and adjusts the coarsening processes accordingly.

Adaptive Smoothed Aggregation ( α SA ) Multigrid ∗

An extension of the SA method in which good convergence properties are achieved in situations where explicit knowledge of the near-kernel components is unavailable is introduced in an adaptive process that uses the method itself to determine near- kernel components and adjusts the coarsening processes accordingly.

Distance‐two interpolation for parallel algebraic multigrid

It is shown that the increased interpolation accuracy largely restores the scalability of AMG convergence factors for PMIS‐coarsened grids, and in combination with complexity reducing methods, such as interpolation truncation, one obtains a class of parallel AMG methods that enjoy excellent scalability properties on large parallel computers.
...